Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–5 of 5 results for author: Dhamecha, T I

Searching in archive cs. Search in all archives.
.
  1. arXiv:2607.21961  [pdf, ps, other

    cs.CL

    On Improving Faithfulness of Podcasts from Documents

    Authors: Soumya Dutta, Tejas Indulal Dhamecha, Pannaga Shivaswamy

    Abstract: Large language models (LLMs) are increasingly used to generate long-form conversational content such as podcasts from textual sources. While these systems produce fluent and engaging narratives, they often introduce ungrounded information. In this work, we present the first systematic study of faithfulness in document-grounded podcast generation, where grounding must be maintained across conversat… ▽ More

    Submitted 24 July, 2026; originally announced July 2026.

    Comments: Under Submission

  2. arXiv:2407.09879  [pdf, ps, other

    cs.CL

    sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting

    Authors: Sanchit Ahuja, Kumar Tanmay, Hardik Hansrajbhai Chauhan, Barun Patra, Kriti Aggarwal, Luciano Del Corro, Arindam Mitra, Tejas Indulal Dhamecha, Ahmed Awadallah, Monojit Choudhary, Vishrav Chaudhary, Sunayana Sitaram

    Abstract: Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively au… ▽ More

    Submitted 18 June, 2025; v1 submitted 13 July, 2024; originally announced July 2024.

    Comments: 20 pages, 12 tables, 5 figures

  3. arXiv:2301.01015  [pdf, other

    cs.CV cs.AI cs.CL

    Semi-Structured Object Sequence Encoders

    Authors: Rudra Murthy V, Riyaz Bhat, Chulaka Gunasekara, Siva Sankalp Patel, Hui Wan, Tejas Indulal Dhamecha, Danish Contractor, Marina Danilevsky

    Abstract: In this paper we explore the task of modeling semi-structured object sequences; in particular, we focus our attention on the problem of developing a structure-aware input representation for such sequences. Examples of such data include user activity on websites, machine logs, and many others. This type of data is often represented as a sequence of sets of key-value pairs over time and can present… ▽ More

    Submitted 22 May, 2023; v1 submitted 3 January, 2023; originally announced January 2023.

  4. arXiv:2109.10534  [pdf, other

    cs.CL

    Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages

    Authors: Tejas Indulal Dhamecha, Rudra Murthy V, Samarth Bharadwaj, Karthik Sankaranarayanan, Pushpak Bhattacharyya

    Abstract: We explore the impact of leveraging the relatedness of languages that belong to the same family in NLP models using multilingual fine-tuning. We hypothesize and validate that multilingual fine-tuning of pre-trained language models can yield better performance on downstream NLP applications, compared to models fine-tuned on individual languages. A first of its kind detailed study is presented to tr… ▽ More

    Submitted 22 September, 2021; originally announced September 2021.

    Comments: Accepted in EMNLP 2021

  5. arXiv:1902.09183  [pdf, other

    cs.CL

    Joint Multi-Domain Learning for Automatic Short Answer Grading

    Authors: Swarnadeep Saha, Tejas I. Dhamecha, Smit Marvaniya, Peter Foltz, Renuka Sindhgatta, Bikram Sengupta

    Abstract: One of the fundamental challenges towards building any intelligent tutoring system is its ability to automatically grade short student answers. A typical automatic short answer grading system (ASAG) grades student answers across multiple domains (or subjects). Grading student answers requires building a supervised machine learning model that evaluates the similarity of the student answer with the… ▽ More

    Submitted 25 February, 2019; originally announced February 2019.

    Comments: 11 pages